Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Features
Speaker Deck
PRO
Sign in
Sign up for free
Search
Search
突然ですが「生涯成績」占ってもいいですか? - プロ野球選手成績予測2022
Search
Shinichi Nakagawa
PRO
April 02, 2022
Research
0
340
突然ですが「生涯成績」占ってもいいですか? - プロ野球選手成績予測2022
とあるLT会で雑に話したプロ野球選手成績予測ネタ
#機械学習 #BigQuery #Python #BIGBOSS #北海道日本ハムファイターズ
Shinichi Nakagawa
PRO
April 02, 2022
Tweet
Share
More Decks by Shinichi Nakagawa
See All by Shinichi Nakagawa
生成AIを活用した野球データ分析 - メジャーリーグ編 / Baseball Analytics for Gen AI
shinyorke
PRO
1
530
ゼロから始めるSREの事業貢献 - 生成AI時代のSRE成長戦略と実践 / Starting SRE from Day One
shinyorke
PRO
0
300
AI・LLM事業部のSREとタスクの自動運転
shinyorke
PRO
0
430
実践Dash - 手を抜きながら本気で作るデータApplicationの基本と応用 / Dash for Python and Baseball
shinyorke
PRO
2
3.2k
Terraform, GitHub Actions, Cloud Buildでデータ基盤をProvisioningする / Data Platform provisioning for Google Cloud and Terraform
shinyorke
PRO
2
3.3k
Cloud RunとCloud PubSubでサーバレスなデータ基盤2024 with Terraform / Cloud Run and PubSub with Terraform
shinyorke
PRO
9
4.1k
自らを強いエンジニアにするための3つの習慣 / I need to be myself, I can't be no one else
shinyorke
PRO
84
86k
阪神タイガース優勝のひみつ - Pythonでシュッと調べた件 / SABRmetrics for Python
shinyorke
PRO
1
1.4k
Pythonとクラウドと野球の推し活. / Baseball Data Platform for Python and Google Cloud
shinyorke
PRO
2
3k
Other Decks in Research
See All in Research
ストレス計測方法の確立に向けたマルチモーダルデータの活用
yurikomium
0
990
90 分で学ぶ P 対 NP 問題
e869120
19
7.8k
数理最適化に基づく制御
mickey_kubo
6
700
SSII2025 [TS2] リモートセンシング画像処理の最前線
ssii
PRO
7
3k
EOGS: Gaussian Splatting for Efficient Satellite Image Photogrammetry
satai
4
370
When Submarine Cables Go Dark: Examining the Web Services Resilience Amid Global Internet Disruptions
irvin
0
260
Large Language Model Agent: A Survey on Methodology, Applications and Challenges
shunk031
14
9.4k
A multimodal data fusion model for accurate and interpretable urban land use mapping with uncertainty analysis
satai
3
250
LLM-as-a-Judge: 文章をLLMで評価する@教育機関DXシンポ
k141303
3
850
Google Agent Development Kit (ADK) 入門 🚀
mickey_kubo
2
1.4k
IMC の細かすぎる話 2025
smly
2
500
Adaptive Experimental Design for Efficient Average Treatment Effect Estimation and Treatment Choice
masakat0
0
150
Featured
See All Featured
Rails Girls Zürich Keynote
gr2m
95
14k
Imperfection Machines: The Place of Print at Facebook
scottboms
267
13k
The Web Performance Landscape in 2024 [PerfNow 2024]
tammyeverts
8
750
Stop Working from a Prison Cell
hatefulcrawdad
271
21k
Easily Structure & Communicate Ideas using Wireframe
afnizarnur
194
16k
Unsuck your backbone
ammeep
671
58k
Connecting the Dots Between Site Speed, User Experience & Your Business [WebExpo 2025]
tammyeverts
8
420
Building a Scalable Design System with Sketch
lauravandoore
462
33k
[Rails World 2023 - Day 1 Closing Keynote] - The Magic of Rails
eileencodes
35
2.5k
Refactoring Trust on Your Teams (GOTO; Chicago 2020)
rmw
34
3.1k
Rebuilding a faster, lazier Slack
samanthasiow
83
9.1k
Fight the Zombie Pattern Library - RWD Summit 2016
marcelosomers
234
17k
Transcript
ಥવͰ͕͢ʮੜ֔ʯ͍͍ͬͯͰ͔͢? Shinichi Nakagawa(@shinyorke)
͋ɺٿબखͷʮੜ֔ʯͰ͢Α
ຊͷࢼ߹ • Python + BigQueryͰͪΐͬͱͨ͠ػցֶशΛΔํ๏ • ࠓϓϩٿͰ͍ͨ͠एखબखͷઌΛ͏ • BIG BOSSͱ(ry
ࣗݾհ • Shinichi Nakagawaʢத ৳Ұʣ • WebܥϑϧαΠΫϧɾΤϯδχΞʢML, Backend, SRE, Frontendʣ
• झຯ͓ΑͼݩͷࣄʮٿΤϯδχΞ݉σʔλαΠΤϯςΟετʯ • Python, Google Cloud, ٿ౷ܭֶͷਓ • ৽ঙ߶ࢤͷϓϨʔΛ͖͔͚ͬʹٿϑΝϯʹͳͬͨ
ϓϩٿબखͷ༧ଌΛ ͍͍ײ͡ʹߦ͏ํ๏ʢμΠδΣετʣ
ΞʔΩςΫνϟʢ֓ཁʣ σʔλΛͱΓ͋͑ͣBigQueryʹೖΕΔ, ੳJupyterLab WebΞϓϦʹ͢ΔͳΒStreamlitͰ͍͍ײ͡ʹग़དྷ·͢
ϓϩٿબखͷ༧ଌϞσϧ 1.༧ଌ͍ͨ͠બखʹࣅ͍ͯΔબखΛۙࣅ࠷ۙ୳ࡧͰநग़ ʢ௨ࢉΛಛྔʹ͍ͯۙ͠͠બखΛϐοΫΞοϓʣ 2.↑Ͱग़ͨ͠ࣅ͍ͯΔબखͷྸຖͷΛग़͢ 3.↑ͷྸຖฏۉΛ༧ଌͱͯ͠ѻ͏ ϝδϟʔϦʔάͷެ։σʔληοτΛར༻ʢͯ͢ӳޠʣ
ֆʹ͢Δͱ͜͏͍͏ྲྀΕ. ۩ମతͳߟ͑ํɾΞϓϩʔνPyCon JP 2020Ͱ͓Λͨ͠ͷͰͦͪΒΛ͝ཡ͍ͩ͘͞. https://shinyorke.hatenablog.com/entry/baseball-and-ml-with-python
ඵͰղઆʮ2022ϓϩٿͷݟͲ͜Ζʯ • BIG BOSSര • ࡳຈυʔϜ, ࠷ޙͷγʔζϯʢຊڌͱͯ͠ʣ • ݱબखυϥϑτɹ˞ະఆͰ͕͢ಋೖͷՄೳੑ͋Γ㽂 •
ϑϨογϡͳएखબखͷ׆༂ʢ༧ఆʣ
ϑϨογϡͳएखબखͷ׆༂Λ༧ • ࢲ͕ਪ͍ͯ͠ΔւಓຊϋϜϑΝΠλʔζͷएखબख • ͷճΓͷಉ྅Β༑ਓΒ͔ΒϦΫΤετ͕͋ͬͨएखબख • ͜ΕΒΛݩʹ, ʮएͯ͘কདྷ׆༂ͦ͠͏ʯͳબखͷΛ༧
AIͰ͏ʮظͷएखϓϩٿબखʯ • ԣDeNAϕΠελʔζظͷγϣʔτʮ ܟేʯ • ౡ౦༸ΧʔϓظͷεϐʔυελʔʮӉ جʯ • BIG BOSSʹ࠷͍ۙͷϑΟδΧϧϞϯελʔʮສ
தਖ਼ʯ 5ઌͷଧɾώοτɾຊྥଧɾଧΛ༧ଌ͠·ͨ͠
Ұਓʮ ܟేʢΓ ͚͍ͱʣʯ • ԣDeNAϕΠελʔζɾख • 2019υϥϑτ1ҐʢۅӂֶԂߴʣ • ମೳྗൈ܈ͷγϣʔτ, ԣظͷ
5ͨͳ͍ͱ͍͚ͳ͍ͬΆ͍ʢখʣ
ܟేͷ༧ଌ • ࠓͷ༧ʮଧ.211 ຊྥଧ6ຊ ଧ37ʯ • ଧ͕͜ΕͰ6ຊϗʔϜϥϯଧͯͨΒٯʹظͰ͖ͦ͏ • 5ޙʮଧ.286
ຊྥଧ6ຊ ଧ50ʯͳͷͰϙδΕͦ͏
ೋਓʮӉ جʢ͏͙͞ ͜͏͖ʣʯ • ౡ౦༸Χʔϓɾ֎ख • 2019υϥϑτ2Ґʢ๏େֶʣ • εϐʔυ͕ചΓͷ֎ख, MLBʹҠ੶ͨ͠ླͷޙ佂ީิ
͜ͷ, Ϡό͘ͳ͍Ͱ͔͢ʢ͑ʣ
Ӊ جͷ༧ଌ • ࠓͷ༧ʮଧ.262 ຊྥଧ33ຊ ଧ87ʯ • ͜Εྲྀੴʹग़དྷ͗͢Ͱ🤔ϗϯτʹ࣮ݱͨ͠ΒදϨϕϧ • 5ޙʮଧ.294
ຊྥଧ24ຊ ଧ86ʯϦΞϧʹग़ͦ͠͏
ࡾਓʮສ தਖ਼ʢ·ΜͳΈ ͪΎ͏͍ͤʣʯ • ւಓຊϋϜϑΝΠλʔζɾ֎ख • 2018υϥϑτ4Ґʢԣߴߍʣ • ύϫʔͱεϐʔυ, ࡶ͞Λ݉Ͷἧ͑ͨϑΟδΧϧϞϯελʔ
ϓϨʔελΠϧݱ࣌ͷBIG BOSSʹඇৗʹ͍ۙ
͜ΕϦΞϦςΟᷓΕΔ
ສ தਖ਼ͷ༧ଌ • ࠓͷ༧ʮଧ.250 ຊྥଧ26ຊ ଧ66ʯ • ελϝϯػձ૿͑ͨΒΓͦ͏ͳࣈ • 5ޙʮଧ.254
ຊྥଧ23ຊ ଧ77ʯ BIG BOSSͷݱ࣌ͬΆ͍ࣈͳΜͰ͢Α͜ͷงғؾ
ສ தਖ਼ͱBIG BOSS ଧ ຊྥଧ ଧ #*(#044ࡀ ʢࡕਆ࣌ʣ
ຊ ଧ ສதਖ਼ࡀ ʢͷ༧ଌʣ ຊ ଧ ΊͬͪΌࣅͯ·ͤΜ͔?
͖͏AIͰBIG BOSSͷޙܧऀ, ݟ͚ͭ·ͨ͠ʢ͜ͳΈʣ
ήʔϜηοτ⚾ ͝ਗ਼ௌ͋Γ͕ͱ͏͍͟͝·ͨ͠. Shinichi Nakagawa(Twitter/Facebook/etc… @shinyorke)